{"id":"W2027399021","doi":"10.1177/0265532207076363","title":"The challenges of the Ontario Secondary School Literacy Test for second language students","year":2007,"lang":"en","type":"article","venue":"Language Testing","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Literacy; Test (biology); Psychology; Mathematics education; Vocabulary; Context (archaeology); Reading (process); English as a second language; Language proficiency; Language assessment; Pedagogy; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001796755,0.0003662097,0.0004718106,0.001136213,0.001441787,0.0015697,0.0007051223,0.0004226475,0.002210685],"category_scores_gemma":[0.01481812,0.0001956697,0.0003705626,0.001220336,0.0006230456,0.000473904,0.001089984,0.0004886069,0.0007555356],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004974371,"about_ca_system_score_gemma":0.01111162,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.5516672,"about_ca_topic_score_gemma":0.7850741,"domain_scores_codex":[0.9976742,0.0002506638,0.0001910837,0.0001413319,0.001440644,0.0003020704],"domain_scores_gemma":[0.9934663,0.001206819,0.0008911825,0.000257354,0.002795786,0.001382542],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002638228,0.0003008131,0.9281842,0.00005953989,0.00002687856,0.0003953329,0.003645854,0.0001857842,0.002151959,0.0004579008,0.006141947,0.05818605],"study_design_scores_gemma":[0.00001634382,0.0001283059,0.9943805,0.00001775519,0.000007187971,0.00009296866,0.001107603,0.0003258138,0.0004552353,0.00009974081,0.003358815,0.000009631814],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9835206,0.0002173342,0.000281047,0.0005691026,0.00003835203,0.0001084047,0.0005088436,0.00003546198,0.01472085],"genre_scores_gemma":[0.9949885,0.0001166404,0.0006515359,0.00008861466,0.000009011625,0.00007516584,0.000652091,0.00001155566,0.003406747],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9950256,"threshold_uncertainty_score":0.9019463,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02266960080524535,"score_gpt":0.3419876094318603,"score_spread":0.319318008626615,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}